Research Publications

RSAC Research publishes papers and reports at conferences, journals, and other outlets.

 

Recent Publications

• Athanasios Theocharis, Armin Buescher, Omer Akgul, Dario Pasquini, Oystein Fladby, Dan Marino, Christopher Gates, Petros Efstathopoulos;Know-It-All?: A Human-Calibrated LLM Benchmark for Cybersecurity Knowledge
• Dario Pasquini, RSAC Labs; Evgenios M. Kornaropoulos and Giuseppe Ateniese, George Mason University. LLMmap: Fingerprinting for Large Language Models. In Proceedings of the 34 USENIX Security Symposium, 2025
• Xiaoyuan Wu, Weiran Lin and Lujo Bauer, Carnegie Mellon University; Omer Akgul, Carnegie Mellon University/RSAC Labs. Estimating LLM Consistency: A User Baseline vs Surrogate Metrics. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)
• Maximiliane Windl, LMU Munich/Munich Center for Machine Learning (MCML); Omer Akgul, Carnegie Mellon University/RSAC Labs; Nathan Malkin, New Jersey Institute of Technology; Lorrie Faith Cranor, Carnegie Mellon University. Privacy Solution or Menace? Investigating Perceptions of Radio-Frequency Sensing. In Proceedings of the 34 USENIX Security Symposium, 2025
• Niklas Pfister, Vaclav Volhejn and Manuel Knott, Lakera AI; Athanasios Theocharis RSAC Labs, et. al. Gandalf the Red: Adaptive Security for LLMs. In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025)